google-videos-search
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes
bash,curl, andpython3to handle search requests and process API responses. - [EXTERNAL_DOWNLOADS]: Fetches search result data from the Frevana API endpoint at
ai-factory.frevana.com. - [DYNAMIC_EXECUTION]: Uses static Python heredocs to perform safe JSON parsing, payload construction, and response validation, avoiding unsafe shell interpolation of user data.
- [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it ingests untrusted search results from the web.
- Ingestion points: The SerpAPI response body retrieved from
ai-factory.frevana.cominscripts/search_google_videos.sh. - Boundary markers: None; the raw search results are passed back to the agent context as JSON.
- Capability inventory: The skill possesses network communication capabilities (
curl) and file system write capabilities (via the--outputparameter). - Sanitization: The script validates that the API response is well-formed JSON but does not filter or sanitize the content of the search results.
Audit Metadata